Skip to main content Skip to main navigation


Keep It Up: In-session Dropout Prediction to Support Blended Classroom Scenarios

N. Rzepka; K. Simbeck; H.-G. Müller; Niels Pinkwart
In: Proceedings of the 14th International Conference on Computer Supported Education. International Conference on Computer Supported Education (CSEDU), April 22-24, Online, Pages 131-138, Vol. 2, ISBN 978-989-758-562-3, SciTePress, 2022.


Dropout prediction models for Massive Open Online Courses (MOOCs) have shown high accuracy rates in the past and make personalized interventions possible. While MOOCs have traditionally high dropout rates, school homework and assignments are supposed to be completed by all learners. In the pandemic, online learning platforms were used to support school teaching. In this setting, dropout predictions have to be designed differently as a simple dropout from the (mandatory) class is not possible. The aim of our work is to transfer traditional temporal dropout prediction models to in-session dropout prediction for school-supporting learning platforms. For this purpose, we used data from more than 164,000 sessions by 52,000 users of the online language learning platform We calculated time-progressive machine learning models that predict dropout after each step (completed sentence) in the assignment using learning process data. The multilayer perceptron is outperforming the baseline algorithms with up to 87% accuracy. By extending the binary prediction with dropout probabilities, we were able to design a personalized intervention strategy that distinguishes between motivational and subject-specific interventions.